Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box jailbreak methods primarily rely on adversarial textual prompts or image perturbations, yet these approaches are highly detectable by standard content filtering systems and exhibit low query and computational efficiency. In this work, we present Cross-modal Adversarial Multimodal Obfuscation (CAMO), a novel black-box jailbreak attack framework that decomposes malicious prompts into semantically benign visual and textual fragments. By leveraging LVLMs' cross-modal reasoning abilities, CAMO covertly reconstructs harmful instructions through multi-step reasoning, evading conventional detection mechanisms. Our approach supports adjustable reasoning complexity and requires significantly fewer queries than prior attacks, enabling both stealth and efficiency. Comprehensive evaluations conducted on leading LVLMs validate CAMO's effectiveness, showcasing robust performance and strong cross-model transferability. These results underscore significant vulnerabilities in current built-in safety mechanisms, emphasizing an urgent need for advanced, alignment-aware security and safety solutions in vision-language systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencySimilar Papers 제목 키워드 기반
StructuralSleight: Automated Jailbreak Attacks on Large Language Models Utilizing Uncommon Text-Organization Structures
Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character…
Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling
Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretabil…
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to…
LLM JailbreakSafety AlignmentPlentiful Jailbreaks with String Compositions
Large language models (LLMs) remain vulnerable to a slew of adversarial attacks and jailbreaking methods. One common approach employed by white-hat attackers, or red-teamers, is to process model inputs and outputs using …
Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs
Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs) transform a harmful query into a concealed multimodal input to bypass safety mechanisms. We show that such attacks are governed by a …